ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no ggml_cuda_init: found 1 ROCm devices: Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32 | model | size | params | backend | ngl | fa | test | t/s | | ------------------------------ | ---------: | ---------: | ---------- | --: | -: | --------------: | -------------------: | | nemotron_h_moe 31B.A3.5B Q4_K - Medium | 21.26 GiB | 31.58 B | ROCm | 99 | 1 | pp512 | 1851.56 ± 12.91 | | nemotron_h_moe 31B.A3.5B Q4_K - Medium | 21.26 GiB | 31.58 B | ROCm | 99 | 1 | tg128 | 105.15 ± 0.53 | build: 2aa45ef9e (7423)